load_pdf
AI agents call load_pdf to retrieve information from PDF Redaction MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Loading a PDF is a retrieval operation with no side effects on the document itself. It prepares data for downstream operations but does not create, modify, or delete content. Classified as Read due to its non-destructive nature and primary function of querying/accessing document content.
From the tool's definition Tool name 'load_pdf' combined with server context indicating 'loading, reviewing, and redacting' documents. The tool loads PDF content into memory for subsequent review or redaction operations.
Attacks that exploit this kind of access
load_pdf. It is categorised as a Read tool in the PDF Redaction MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PDF Redaction MCP Server MCP server in PolicyLayer and add a rule for load_pdf: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches PDF Redaction MCP Server. Nothing to install.
load_pdf is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the load_pdf rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for load_pdf. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
load_pdf is provided by the PDF Redaction MCP Server MCP server (marc-hanheide/redact_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →